Intelligent Monitoring Method, Device, System, and Storage Medium

Abstract

This application provides an intelligent monitoring method, device, system, and storage medium. These methods intelligently analyze target object image data to obtain the target object's posture information and obtain the target object's ranging location. Based on the ranging information, the method calculates the height from the ranging location to a reference surface, obtains corresponding height information, and finally combines the posture and height information to determine whether the target object is currently in a predetermined risk state. Because the determination of the risk state incorporates the target object's posture characteristics and the height characteristics from the ranging location to the reference surface, the monitoring results are highly accurate.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method, device and system, and storage medium. Background Art

[0002] With the development of social economy, the problem of aging population is becoming more and more serious, and the demand for home monitoring of the elderly is becoming stronger. In most families, children have to go out to work and have to leave the elderly alone at home. The elderly are older and have poor physical fitness. In addition, their eyesight is weakened and they are prone to falls. If they are not discovered in time, they may miss the best time for treatment. Therefore, many smart monitoring devices have come into being.

[0003] Among the existing smart monitoring devices for elderly people at home, most wearable elderly fall monitoring devices have problems such as difficult installation and inaccurate detection. Video-based elderly fall monitoring devices need to use visible light to collect images for behavioral analysis to monitor the elderly's activities in real time. Therefore, the accuracy of their monitoring will be affected by the light in the monitored environment. In addition, visible light video monitoring also poses certain risks to the privacy protection of the elderly's lives. Summary of the Invention

[0004] In order to solve the existing technical problems, the present application provides an intelligent monitoring method, device, system, and storage medium that can accurately monitor whether the monitored target object has fallen.

[0005] To achieve the above objectives, the technical solution of the embodiment of the present application is implemented as follows:

[0006] An intelligent monitoring method, comprising:

[0007] Acquire image data of the target object;

[0008] Performing intelligent analysis on the target object in the image data to obtain posture information of the target object;

[0009] Obtaining ranging information corresponding to the ranging part of the target object;

[0010] Calculate the height from the distance measurement part of the target object to the reference surface according to the distance measurement information to obtain height information;

[0011] Determine whether the target object is currently in a set risk state according to the posture information and the height information.

[0012] An intelligent monitoring device, comprising:

[0013] An image acquisition module, used for acquiring image data of a target object;

[0014] A distance measuring module, configured to measure the distance of the distance measuring part of the target object to obtain the distance measuring information of the target object;

[0015] a storage module for storing computer programs;

[0016] A processing module is provided, wherein the processing module obtains the image data and the ranging information and implements the steps of the intelligent monitoring method when running the computer program.

[0017] An intelligent monitoring system, characterized in that it includes the intelligent monitoring device, cloud and terminal device. The intelligent monitoring device is used to report information that the target object is currently in a set risk state to the cloud. The cloud sends matching early warning information to the corresponding terminal device based on the current risk state of the target object.

[0018] A computer-readable storage medium stores a computer program, and when the computer program is executed by hardware, the intelligent monitoring method can be implemented.

[0019] The intelligent monitoring method, apparatus, device, system, and storage medium provided herein intelligently analyze target object image data to obtain the target object's posture information and the target object's ranging location. Based on the ranging information, the method calculates the height from the ranging location to a reference surface, and obtains the corresponding height information. Finally, the method combines the posture and height information to determine whether the target object is currently in a predetermined risk state. Because the determination of the risk state incorporates the target object's posture characteristics and the height characteristics from the ranging location to the reference surface, the monitoring results are highly accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the drawings. In the drawings:

[0021] Figure 1 This is a flow chart of the intelligent monitoring method according to certain embodiments of the present application;

[0022] Figure 2 This is a schematic diagram of a module of an intelligent monitoring device according to certain embodiments of the present application;

[0023] Figure 3 This is a schematic diagram of a module of an intelligent monitoring device according to certain embodiments of the present application;

[0024] Figure 4 This is a schematic diagram of a module of an intelligent monitoring device according to certain embodiments of the present application;

[0025] Figure 5This is a flow chart of the intelligent monitoring method according to certain embodiments of the present application;

[0026] Figure 6 This is a schematic diagram of the installation and application of the intelligent monitoring device according to certain embodiments of the present application;

[0027] Figure 7 A schematic diagram of the structure of a smart monitoring device from a first perspective in certain embodiments;

[0028] Figure 8 A schematic diagram of the structure of a smart monitoring device from a second perspective in certain embodiments;

[0029] Figure 9 A schematic diagram of the structure of an intelligent monitoring device from a third perspective according to certain embodiments;

[0030] Figure 10 A schematic diagram of the structure of an intelligent monitoring system according to certain embodiments. DETAILED DESCRIPTION

[0031] The technical solution of this application is further elaborated in detail below with reference to the accompanying drawings and specific embodiments.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein in the specification of this application are intended only to describe specific embodiments and are not intended to limit the implementation of this application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0033] In the description of this application, it should be understood that the terms "center," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended only to facilitate the description of this application and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting this application. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0034] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to direct connections, indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on specific circumstances.

[0035] Figure 1 The figure shows a flow chart of the intelligent monitoring method provided in the embodiment of the present application. Figure 2 To be used to implement Figure 1 The module diagram of the intelligent monitoring device of the intelligent monitoring method shown is as follows, Figure 3 To be used to implement Figure 1 Schematic diagram of the modules of the intelligent monitoring device of the intelligent monitoring method shown.

[0036] refer to Figure 1 As shown, in some embodiments, the intelligent monitoring method includes the following steps:

[0037] S100: Acquire image data of a target object.

[0038] Specifically, S100 can be executed by the first acquisition module 011 in the intelligent monitoring device 01 provided herein, or by the storage module 023 in the intelligent monitoring device 02 provided herein storing an image acquisition program. The processing module 024 in the intelligent monitoring device 02 then executes the image acquisition program to obtain corresponding image data from the image acquisition module 021 in the intelligent monitoring device 02. In this embodiment, the image acquisition module is an infrared thermal imaging module, such as an infrared thermal imager, and therefore the image data in S100 is infrared image data. As can be seen from the imaging principle of an infrared thermal imager, infrared image data contains image information and temperature information of the target object, as well as the ambient temperature of the target object's environment and temperature information of other objects in the scene. Intelligent monitoring based on infrared image data ensures the privacy of the target object because only the target object's outline can be identified during monitoring, not its face.

[0039] In this embodiment, the target object is an elderly person within the monitoring range, such as an elderly person living alone. In other embodiments, the target object can also be a child or other person who needs to be intelligently monitored. In addition, in this embodiment, the image data of the target object is a picture of the target object, which includes background information of the target object's environment and information about the target object itself, such as its outline information.

[0040] It should be noted here that, in this embodiment, acquiring the image data of the target object is a continuous acquisition process, and one frame of image data is acquired each time. The image data acquisition action is a real-time action or is performed once at a preset interval, that is, the first acquisition module 011 or the processing module 024 acquires a frame of image data in real time or at a preset interval and stores it.

[0041] S200: Performing intelligent analysis on the target object in the image data to obtain corresponding posture information.

[0042] S200 is executed by the intelligent analysis module 012 in the intelligent monitoring device 01, or the intelligent analysis program is stored by the storage module 023 in the intelligent monitoring device 02, and then the intelligent analysis program is run by the processing module 024 to perform intelligent analysis on each frame of image data obtained in S100 in turn, thereby obtaining the posture information corresponding to each frame of image data, and further storing the corresponding posture information.

[0043] When a person falls, the distance between his or her center of gravity and the ground will decrease, and it is generally believed that the posture when falling is a lying posture. Therefore, when a person's posture changes, if the posture change corresponds to a decrease in the center of gravity, and the final change is a lying posture, it means that the monitored person may currently be in a falling state or a normal lying state, that is, a static state. After that, it is only necessary to distinguish between the falling state and the static state. Therefore, it is necessary to identify and analyze the posture of the target object to obtain the corresponding posture information, and the posture information includes standing posture, sitting posture, and lying posture. In some embodiments, in order to improve the accuracy of intelligent monitoring, the intelligent analysis of the posture of the target object further includes identifying the squatting posture of the target object to distinguish it from the lying posture.

[0044] S300: Acquire distance information from the distance measurement part of the target object to the reference surface height.

[0045] Specifically, the distance information may be collected and generated by the distance measurement module 022 in the intelligent monitoring device 02 , and then the second acquisition module 013 in the intelligent monitoring apparatus 01 acquires the distance information from the distance measurement module 022 .

[0046] S400: Calculate the height from the distance measurement part of the target object to the reference surface according to the distance information to obtain height information.

[0047] Specifically, the calculation module 014 in the intelligent monitoring device 01 or the processing module 024 in the intelligent monitoring device 02 calculates the height information of the ranging part of the target object to the reference surface based on the ranging information, the installation height information of the ranging module to the reference surface (such as the ground), and the rotation angle information of the ranging module.

[0048] In some embodiments, the intelligent monitoring device 01 further includes a target positioning module and a target tracking module to locate and track the target object in the image data to obtain target positioning data and target tracking data, and then determine the ranging position of the target object based on the target positioning data and target tracking data, so that the ranging module can adjust the ranging angle to measure the ranging position.

[0049] In some embodiments, the distance measurement module is a laser distance measurement module. The storage module 023 in the intelligent monitoring device 02 also stores a height information acquisition program, and the processing module 024 executes S400 according to the height information acquisition program.

[0050] S500: Determine whether the target object is currently in a preset risk state based on the posture information and the height information.

[0051] The risk states preset in S500 include, but are not limited to, a fall risk state and an inactivity timeout risk state. A fall risk state refers to a state in which the subject is in danger of falling, while an inactivity timeout risk state refers to a state in which the subject remains in an inactivity state for a duration exceeding a preset value. One possible scenario in which the subject may be in an inactivity state is resting. However, if the duration of resting exceeds a typical time, it indicates that the subject may be in a risk state.

[0052] For target subjects such as elderly people living alone, children, or patients with physical discomfort, falling is a common and highly probable occurrence, so it is necessary to monitor their falling status. Falling is a very fast movement process. During the fall, the distance between the center of gravity of the human body and the ground changes significantly, and the human body's posture also changes significantly. For example, when a person changes from a standing or sitting position to a lying position, it can be determined whether the target subject is currently in a static state or a falling state. Then, the value of the height information of the human body in the lying position is compared with the corresponding preset value. If the former is less than or equal to the latter, it indicates that the target subject is currently in a falling state. Otherwise, it is in a static state (i.e., a lying state or a static lying state). After determining that the target subject is in a risk state of falling, the risk state information of falling needs to be reported, for example, to the cloud, which is then sent to the user terminal by the cloud. When it is determined that the target subject is currently in a static state, it is necessary to further monitor the duration of the static state to determine whether the duration exceeds the preset value. If it exceeds, the target subject is determined to be in a risk state of static timeout, and the risk state information is further reported to the terminal user. Therefore, the posture information obtained in S200 and the height information obtained in S400, i.e., the posture characteristics of the fall and the characteristics of the fallen object above the ground, can be combined to accurately determine whether the target object has currently fallen, that is, whether it is at risk of falling. Specifically, S500 can be executed by the determination module 015 in the intelligent monitoring device 01, or the storage module 023 in the intelligent monitoring device can store a fall determination program, and then the processing module 024 implements S800 when running the fall determination program.

[0053] As can be seen from the above, the intelligent monitoring method provided by this application intelligently analyzes the target object's image data to obtain the target object's posture information, obtains the target object's ranging location, calculates the height from the ranging location to a reference surface based on the ranging information, and obtains the corresponding height information. Finally, the posture and height information are combined to determine whether the target object is currently in a set risk state. Because the risk state determination process combines the target object's posture characteristics and the height characteristics of the target object's ranging location from the reference surface, the monitoring results are highly accurate.

[0054] In some embodiments, the height variation trend from the distance measurement position to the reference surface is the same as the height variation trend from the center of gravity of the target object to the reference surface. Further, S300 includes the following steps:

[0055] S301: Determine whether the posture of the target object has changed based on the posture information obtained in S200.

[0056] Correspondingly, the second acquisition module further includes a posture change judgment submodule and a height information acquisition submodule. The posture change judgment submodule compares the posture information currently obtained in S200 (the posture information obtained by performing intelligent analysis on the image data of the current frame obtained in S100) and the adjacent upper posture information (the posture information obtained by performing intelligent analysis on the image data of the previous frame adjacent to the image data of the current frame obtained in S200). If the comparison result is that the former and the latter are the same posture information, for example, both are standing, sitting, squatting, and lying, then the judgment result of S301 is that the posture of the target object has not changed; otherwise, it has changed, and S302 is executed.

[0057] S302: When the posture of the target object changes, start a distance measurement module to measure the distance of the distance measurement part of the target object to obtain distance measurement information.

[0058] Since one of the conditions for determining whether the target object has fallen is that the posture of the target object has changed, in order to reduce the power consumption of the intelligent monitoring device or intelligent monitoring equipment when performing intelligent monitoring, the ranging module 022 (such as a laser rangefinder) can be controlled only to perform corresponding distance detection when the posture of the target object has changed. That is, when the judgment result of S301 is that the current posture of the target object has not changed, the ranging module 022 is not started to measure the distance. Only when the judgment result of S601 is that the current posture of the target object has changed relative to the adjacent previous posture, the posture change judgment submodule controls the ranging module to start to measure the distance to obtain the distance information, so that the corresponding calculation can be performed in S400 according to the distance information obtained in S302 to obtain the height information.

[0059] In some embodiments, when the ranging module starts to measure distance, if the current target object is in a lying position, it is necessary to continuously detect the height of the ranging part of the target object from the reference surface for multiple times to obtain multiple corresponding height information. The second acquisition module obtains a corresponding height information each time, so as to continuously track the duration of the target object in a lying position according to each height information, and perform corresponding processing according to the duration. For example, if the current target object is in a static lying position, the above-mentioned duration will be compared with the preset time. Once it is greater than or equal to the preset time, it is determined that the target object is in a risk state of static timeout, and the information of the static timeout will be reported, such as reported to the cloud, and then sent to the user terminal by the cloud. If the current target object is in a risk state of falling, it is also necessary to continuously follow up the duration of the falling state, and report the duration of the falling so that the user can understand the state of the target object in real time.

[0060] Since the center of gravity of the target object will drop significantly during the fall, it is necessary to obtain the height of the target object's center of gravity to the reference surface. However, the positioning of the target object's center of gravity is relatively complex. In this embodiment, the distance measurement part of the target object is set to the target object's head. The head positioning is simple, and the distance between the target object's head and the reference surface changes significantly during the fall. Therefore, the height of the target object's center of gravity to the reference surface can be characterized by detecting the distance between the target object's head and the reference surface. The reference surface here generally refers to the ground where the target object is located, and also refers to the plane of other locations where the target object may fall.

[0061] In other embodiments, the distance measurement location may be any other part of the target object, as long as the height variation between the location and the reference surface can represent the height variation between the target object's center of gravity and the reference surface. In other words, any location that satisfies the requirement that the height variation trend between the distance measurement location and the ground is the same as the height variation trend between the target object's center of gravity and the ground can be used as the distance measurement location.

[0062] In some embodiments, S500 further includes the following steps:

[0063] S501: When the posture information indicates that the target object is currently in a lying position, determine whether the center of gravity of the target object in the current posture is lowered relative to the center of gravity in the previous posture.

[0064] Accordingly, the determination module further includes a center of gravity determination submodule for executing S501. Alternatively, the storage module 023 in the intelligent monitoring device 02 further stores a center of gravity change determination program, and the processing module 024 executes S501 when running the center of gravity change determination program.

[0065] Specifically, in this embodiment, the center of gravity judgment submodule or processing module 024 implements S501 by comparing the height information obtained when the target object is in the current posture with the height information obtained when the target object is in the previous posture (such as the adjacent previous different posture).

[0066] It should be noted that, as can be seen from the above description, in the present application, as long as the posture of the target object changes, the distance measurement of the distance measurement part of the target object will be performed at least once to obtain the corresponding height information based on the distance measurement information. Therefore, the target object will have corresponding height information in different postures. The current posture refers to the posture obtained by intelligent analysis based on the image data of the current frame obtained in S100, and the previous posture refers to the adjacent previous different posture in this embodiment. The adjacent previous different posture refers to the adjacent previous posture that is different from the current posture. For example, if the postures corresponding to the three consecutive frames of image data corresponding to the target object are standing, lying, and lying respectively, then the current posture is lying, the adjacent previous posture is also lying, and the adjacent previous different posture is standing.

[0067] If the determination result of S501 is that the center of gravity of the target object in the current posture is lower than the center of gravity in the previous different posture, and the posture information in S200 indicates that the current posture of the target object is lying down, S502 is executed.

[0068] S502: Compare the value of the height information obtained when the target object is in the current posture with a preset value.

[0069] The determination module 015 in the intelligent monitoring device 01 further includes a height information comparison submodule for obtaining the height information corresponding to the target object in its current posture to execute S502. Alternatively, the storage module 023 of the intelligent monitoring device 02 may also store a height information comparison program, and the processing module 024 may execute the height information comparison program to implement S502.

[0070] If the comparison result of S502 is that the value of the height information obtained when the target object is in the current posture is less than or equal to the preset value, S503 is executed.

[0071] S503: Determine whether the target object is currently in a risk state of falling.

[0072] Specifically, the determination module 015 further includes a fall determination submodule, which is configured to determine, based on the comparison result of S502 , whether the target object is currently in a risk state of falling.

[0073] In some embodiments, if the comparison result of S502 is that the value of the height information obtained when the target object is in the current posture is greater than the preset value, the intelligent monitoring method provided in this application also includes executing S504, S505, S506, and S507 in sequence after S502.

[0074] S804: Determine that the target object is currently in a stationary state.

[0075] Specifically, the determination module 015 further includes a stationary state determination submodule for executing S504. When the value of the height information obtained when the target object is in the current posture is greater than a preset value, it indicates that the distance measurement part (head) is still a certain distance from the ground. At this time, the target object is in a lying position. Therefore, it can be determined that the target object is currently in a normal lying state. Since the lying position in a non-falling situation generally refers to lying down to rest or sleep, the target object is in a relatively quiet state in this case. Therefore, we define this state as a stationary state.

[0076] S505: Monitor the duration of the target object being in the stationary state.

[0077] Specifically, the determination module 015 further includes a duration monitoring submodule, which is configured to execute S505 , such as timing the stationary state to obtain a corresponding duration.

[0078] S506: Compare the duration with the time threshold.

[0079] Specifically, the determination module 015 further includes a time comparison submodule, which is used to execute S506.

[0080] S507: When the duration exceeds the time threshold, it is determined that the target object is in a risk state of stationary timeout.

[0081] Specifically, the determination module 015 further includes a stationary timeout risk state determination module, which is configured to execute S507.

[0082] In some embodiments, after determining the current risk status of the target object, such as after S503 and / or S507, the intelligent monitoring method provided by the present application further includes:

[0083] S600: Report the current risk status information of the target object.

[0084] Correspondingly, such as Figure 4As shown, the intelligent monitoring device 02 further includes a communication module 025. After obtaining the corresponding risk status, the processing module 024 reports the corresponding risk status information to the cloud through the communication module 025, and then the cloud sends it to the mobile phone terminal or computer of the end user, so that the user can promptly discover the risk status of the target object and perform corresponding processing.

[0085] In some embodiments, as Figure 5 As shown, after S100 and before S200, the intelligent monitoring method provided by the present application further includes:

[0086] S101: Perform target positioning and target tracking on the target object in the image data obtained in S100 to obtain corresponding target positioning data and target tracking data.

[0087] Accordingly, the intelligent monitoring device 01 further includes a target positioning module and a target tracking module. The target positioning module is used to determine the position of the target object in the image data in order to capture the target object from the image data. Furthermore, since the target object may move within the monitoring range, the target tracking module is further required to continuously track the target object's position. In the intelligent monitoring device 02, its storage module 023 also stores a target positioning program and a target tracking program. The processing module 024 executes the target positioning program and the target tracking program, respectively, to implement S301, thereby obtaining corresponding target positioning data and target tracking data.

[0088] S202: According to the target positioning data and the target tracking data, the shooting angle of the image acquisition module of the image data is controlled to adjust the position of the target object in the image data.

[0089] The intelligent monitoring device 01 further includes an adjustment module for executing S302. Image data of the target object is captured and generated by the image acquisition module 021. The captured image data includes the target object and its surrounding background. To facilitate the intelligent analysis in S200, a preferred solution is to adjust the shooting angle of the image acquisition module based on the target positioning data and the target tracking data to adjust the position of the target object in the image data. For example, the target object is adjusted to be centered in the image data to accurately determine the position of the distance measurement part of the target object. Specifically, in the intelligent monitoring device 02 provided in this application, the image acquisition module is driven by a motor assembly. Therefore, the movement direction of the motor assembly can be adjusted in real time based on the corresponding target positioning data and the target tracking data, thereby driving the movement of the image acquisition module to adjust the shooting angle so that the target object is centered in the image data. The motor assembly generally includes two motors that rotate in perpendicular directions.

[0090] In some embodiments, the intelligent monitoring method provided by this application further includes:

[0091] S701: Acquire at least one of the following temperature data: the temperature of the target object, the temperature of the environment where the target object is located, and the highest temperature of the target objects in the scene where the target object is located.

[0092] S702: Compare the acquired temperature data value with the corresponding temperature threshold value. When the temperature data exceeds the corresponding temperature threshold value, determine that the target object is currently in a risk state of abnormal temperature.

[0093] Then, in the above S600, it is also necessary to report the risk status information of abnormal temperature.

[0094] In some embodiments, the image data obtained in S100 is infrared image data captured and generated by an infrared thermal imager, which includes temperature information. By controlling the movement direction of the infrared thermal imager, the image data can include the target object, the environment in which the target object resides, and the temperature monitoring target in the environment in which the intelligent monitoring target resides. The infrared image data obtained in S100 can then be used to obtain temperature data for at least one of the target object, the environment in which the target object resides, and the temperature monitoring target in the environment in which the target object resides. For example, forehead temperature data of the target object can be obtained from the infrared image data and compared with a first threshold temperature (e.g., 37.3 degrees Celsius) to determine whether the target object currently has a fever. Furthermore, ambient temperature data of the target object's environment can be obtained from the infrared image data and compared with a second threshold temperature to determine whether the target object's current environment is within a safe temperature range to prevent fires. Furthermore, the temperature of a high-temperature target (temperature monitoring target) in the environment in which the fallen target monitoring object resides can be obtained and compared with a third threshold temperature to determine whether a corresponding safety hazard currently exists. Therefore, the intelligent monitoring method provided in the present application can perform corresponding monitoring of the physical health status of the target object and the safety status of the environment in which it is located while performing intelligent monitoring, which can effectively reduce the risk of the target object that needs to be monitored.

[0095] Specifically, the intelligent monitoring device further includes a temperature acquisition module and a temperature determination module, configured to execute S701 and S702, respectively. In the intelligent monitoring device, the storage module further stores a temperature acquisition program and a temperature determination program. The processing module implements S701 when executing the temperature acquisition program and implements S702 when executing the temperature determination program.

[0096] In some embodiments, the intelligent monitoring method provided by this application further includes:

[0097] S800: After S100, the number of target objects in the image data is monitored, and the monitored number is compared with a preset number to determine whether there is currently an outsider intrusion in the environment where the target objects are located, and a corresponding warning message is issued.

[0098] Specifically, the intelligent monitoring device 01 further includes a quantity monitoring module for executing S800. In addition, in the intelligent monitoring device 02, the storage module further stores a quantity monitoring program, and the processing module implements S800 when running the quantity monitoring program.

[0099] In addition, if Figure 2 As shown, the present application also provides an intelligent monitoring device for implementing the intelligent monitoring method provided by the present application, and the device mainly includes: a first acquisition module 011, an intelligent analysis module 012, a second acquisition module 013, a calculation module 014, and a determination module 015. Among them, the first acquisition module 011 is used to acquire image data of the target object, the intelligent analysis module 012 is used to perform intelligent analysis on the target object in the image data to obtain the posture information of the target object, the second acquisition module 013 is used to acquire the ranging information of the ranging part of the target object, the calculation module 014 is used to calculate the height of the ranging part of the target object to the reference surface based on the ranging information to obtain height information, and the determination module 015 is used to determine whether the target object is currently in a preset risk state based on the posture information and height information. In addition, the intelligent monitoring device provided by the present application further includes the other corresponding modules described above in the intelligent monitoring method.

[0100] In some embodiments, the present application also provides an installation diagram of a smart monitoring device 02 in an application scenario, such as Figure 6 As shown, the intelligent monitoring device 02 is installed on the ceiling of the room where the target object is located. The main activity plane of the target object is the ground, that is, the ground is an optional plane of the reference plane described above. In order to clearly illustrate the structure of the intelligent monitoring device 02 provided in an embodiment of the present application, Figure 7 Given Figure 6 The first-person perspective structural diagram of the intelligent monitoring device in Figure 8 Given Figure 6 The second perspective structural diagram of the intelligent monitoring device in Figure 9 Given Figure 6 The third perspective structure diagram of the intelligent monitoring device in FIG. Figure 6 The perspective of the ground direction and the ceiling direction in the second perspective is vertical Figure 6 The direction of the plane, the third perspective is given by Figure 6 left to right or right to left direction.

[0101] In some embodiments, the image acquisition module 021 and the ranging module 022 are co-encapsulated in the same package housing to form an infrared module 0212. The storage module 023 and the processing module 024 are integrated into an intelligent processing module 0234. In other embodiments, the storage module and the processing module may also be integrated into an FPGA (Field Programmable Gate Array) module. The image acquisition module 021 is used to acquire image data of the target object, while the ranging module 022 is used to measure the distance of the ranging portion of the target object to obtain distance information. The storage module 023 is used to store a computer program, and the processing module 024 is used to obtain image data from the image acquisition module 021 and distance information from the laser ranging module 022. When the computer program stored in the storage module 023 is executed, any step of the intelligent monitoring method provided in this application is implemented. Since the computer program stored in the storage module and the steps implemented by the processing module have been described in each step when describing the intelligent monitoring method provided in this application, they will not be repeated here.

[0102] The processing module may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the intelligent monitoring device may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0103] The storage module may include a high-speed RAM (Random Access Memory) and may also include an NVM (Non-Volatile Memory), such as at least one disk storage.

[0104] In some embodiments, the image acquisition module is a thermal imager that is used to acquire image data of a target object. Since the acquired image data is infrared image data, it contains corresponding temperature information. Therefore, in the present application, the processing module 024 can also obtain temperature data of at least one of the target object, the environment in which the target object resides, and a temperature monitoring target in the environment in which the target object resides from the infrared image data acquired by the infrared thermal imager, so as to monitor the temperature status of the target object and its environment.

[0105] In some embodiments, ranging module 022 is a laser rangefinder. When the target object's posture changes, processing module 024 issues a start command to activate the laser rangefinder to collect ranging information. Because both the infrared imager and the laser rangefinder need to follow the movement of the intelligent monitoring target during image acquisition and distance measurement, in this application, the thermal imager and the laser rangefinder are packaged in the same housing to form infrared module 0212. This allows for the corresponding movement of the laser rangefinder and infrared imager, while also reducing the size of the intelligent monitoring device.

[0106] The infrared module uses a large array detector: 256*192, and is top-mounted. Taking an installation height of 2.5m as an example, combined with a 120-degree field of view, it can cover an area of about 30 square meters. This method can cover more space to the greatest extent. At the same time, the top-mounted method can reduce blind spots caused by obstructions to a certain extent.

[0107] In some embodiments, the processing module 024 transmits relevant risk status information and related data information, such as fall risk status information, abnormal temperature risk status information, inactivity timeout risk status information, image data, temperature data, and posture information of the target object, to the cloud (e.g., a cloud server) via the communication module 025. The cloud then processes the relevant data obtained from the intelligent monitoring device and sends it to the user's mobile terminal or computer.

[0108] In some embodiments, the communication module 025 is an Internet of Things module, which can transmit data to the server through WiFi, Ble, Zigbee, and smart gateway communication means, or use traditional wired connection methods or more advanced communication modules to realize data transmission between smart monitoring equipment and the server.

[0109] Continue to refer Figures 6 to 9 As shown, the intelligent monitoring device 02 provided herein further includes a first motor 026 and a second motor 027. The first motor 026 is used to adjust the orientation of the image acquisition module 021 in a first direction, and the second motor 027 is used to adjust the orientation of the image acquisition module 021 in a second direction. The first direction is perpendicular to the second direction. The first motor 026 and the second motor 027 rotate accordingly based on control commands output by the processing module 024 to adjust the position of the target object in the image data.

[0110] like Figures 6 to 9As shown, the intelligent monitoring device 02 provided in the present application also includes a fixing base 028 and a bracket 029. In some embodiments, the storage module 023, the processing module 024 and the communication module 025 are all arranged on the fixing base 028. The first side of the fixing base 028 is installed on the mounting surface (such as a ceiling), and the second side thereof opposite to the first side is provided with a first motor 026. The second motor 027, the image acquisition module 021 and the ranging module 022 are provided on the fixing base 028 through the bracket 029, and are provided above the target object through the fixing base 028. Specifically, the first end of the bracket 029 is provided on the second side of the fixing base 28, and the second end is provided with the second motor 027 and the infrared module 0212 (including the image acquisition module 021 and the ranging module 022), wherein the first end and the second end of the bracket 029 are opposite ends.

[0111] In some embodiments, the present application also provides an intelligent monitoring system, the system structure diagram of which is as follows: Figure 10 As shown, it includes the smart monitoring device 02, cloud 03 and terminal device 04 provided according to any embodiment of the present application. Among them, the smart monitoring device 02 is used to report the information that the target object is currently in a set risk state to the cloud 03, and the cloud 04 sends matching warning information to the corresponding terminal 04 device based on the current risk state of the target object.

[0112] In some embodiments, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by hardware, it can implement any step in the intelligent monitoring method provided by the present application.

[0113] In order to have a more comprehensive understanding of the intelligent monitoring method provided in the embodiment of the present application, please refer to Figures 6 to 10 The following takes the intelligent monitoring device including a fixing base 028, an intelligent processing module 0234 (including a storage module and a processing module), an Internet of Things module 025 (a communication module), a bracket 029, a horizontal motor 026, a pitch motor 027, and an infrared module 0212 (including an infrared thermal imaging module 021 and a laser ranging module 022) as an example to specifically illustrate the method flow of the intelligent monitoring device and monitoring system provided by this application for performing intelligent monitoring. The installation and composition diagram of the intelligent monitoring device is shown in FIG. Figures 6 to 9 As shown in the figure, the schematic diagram of the intelligent monitoring system including intelligent monitoring equipment is as follows Figure 10As shown, the infrared thermal imaging module 021 collects image data and temperature data; the intelligent processing module 024 performs target positioning, posture recognition, and target tracking on the target object (elderly person). Based on the target positioning and tracking information, the horizontal motor 026 and the pitch motor 027 are adjusted to keep the target object exactly in the center of the image. The posture information is used to distinguish the target object's posture (standing, sitting, squatting, lying down). When a posture change is detected, the laser ranging module 022 is activated to measure the distance (height) between the target object's ranging part and the ground. When the target object is detected to be lying down, the height between the ranging part and the ground is measured continuously for multiple frames. The posture and height detection can monitor the static state and fall state. At the same time, the device can also detect the temperature of the human body in the target frame and the high-temperature target in the scene, and report the target object's status information, ambient temperature, high-temperature target temperature, and low-temperature target temperature in real time. It can detect indoor temperature and provide early warning of fire. In addition, it can also monitor for intrusion by outsiders, and integrate this information to intelligently monitor the target object. The Internet of Things module 025 transmits this information to the cloud 03 (such as a cloud server), and the terminal 04 obtains the status of the target object and related scene information through the connection with the cloud 03.

[0114] Specifically, in some embodiments, the method steps for performing intelligent monitoring according to the intelligent monitoring system provided by this application are as follows:

[0115] S11: Capturing image information of the target object through the thermal imager 021 in the infrared module 0212 to obtain image data.

[0116] S12: The intelligent processing module 0234 performs intelligent analysis on the image data to obtain target positioning data, target tracking data and posture information of the target object, and outputs the corresponding target positioning data, target tracking data and posture information.

[0117] S13: Determine whether the target object currently has a posture change based on the posture information. When the posture of the target object changes, start the laser rangefinder 022 to detect the distance information of the target object's head (the distance information value is the distance from the ranging module to the target object's head).

[0118] S14: The intelligent processing module 0234 calculates the height from the head of the target object to the ground according to the distance measurement information.

[0119] S15: Determine whether the target object is currently in a lying position based on the posture information. When the target object is in a lying position, the laser rangefinder 022 will continuously detect the distance between the ranging part of the target object and the ground for multiple frames, and compare the corresponding height information with the preset value. When the height information is less than the preset value, it is determined that the target object is currently in a falling state.

[0120] S16: The communication module 025 sends the corresponding fall status information to the cloud 03. The cloud 03 processes the received fall status information accordingly and then sends it to the user terminal 03 so that the user can perform corresponding operations based on the obtained fall status information.

[0121] If in S15, the height information is greater than the preset value, it means that the current target object is in a stationary state, and its stationary state is continuously monitored to obtain the duration of the stationary state, and the corresponding duration is compared with the preset time to determine whether the target object is currently in a risk state of stationary timeout. If so, the corresponding risk information needs to be sent to the cloud 03 through the communication module 025, and finally sent to the user terminal 04 by the cloud 03.

[0122] Furthermore, since image acquisition module 021 is an infrared thermal imager, intelligent processing module 0234 can also obtain the temperature of the target object based on the infrared image data captured by image acquisition module 021 to determine whether the target object has a fever, monitor the temperature of the target object's environment to prevent fires, and monitor the temperature of high-temperature or low-temperature objects in the target object's scene to prevent the risk of abnormal temperatures. Intelligent processing module 0234 can also identify the image data to determine the number of people in the target object's scene and compare the identified number of people with a preset number of people to determine whether there is an intruder.

[0123] The intelligent monitoring method in the above embodiment has at least the following characteristics:

[0124] 1. Combining the changes in the target object's body posture and the changes in the height of the target object's ranging part from the ground, the intelligent processing module performs intelligent analysis on these two features, avoiding false detections caused by a single infrared device and making an accurate judgment on falls through comprehensive information.

[0125] 2. Combined with human posture information and temperature information, a continuous time record is made for static states such as sleeping, and an alarm is processed for states that exceed the time threshold, so as to effectively monitor the health status of the target object.

[0126] 3. Through the ambient temperature information, fire can be detected at an early stage, ensuring the safety of the target object.

[0127] 4. The monitoring information obtained by the intelligent monitoring equipment can be transmitted in a timely manner through the Internet of Things module, so that timely and effective assistance can be provided in unexpected situations, and the elderly can be intelligently monitored by combining this information.

[0128] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An intelligent monitoring method, characterized in that: include: Acquire image data of the target object; performing intelligent analysis on the target object in the image data to obtain posture information of the target object, wherein the target object is located at a center position in the image data; Obtaining ranging information corresponding to the ranging part of the target object; Calculating the height from the distance measurement part of the target object to the reference surface according to the distance measurement information to obtain height information; Determining whether the target object is currently in a set risk state based on the posture information and the height information, wherein determining whether the target object is currently in a set risk state based on the posture information and the height information includes: when the posture information indicates that the target object is currently in a lying position, determining whether the center of gravity of the target object in the current posture is lowered relative to the center of gravity in the previous posture; When the center of gravity of the target object in the current posture drops relative to the center of gravity in the previous posture, the value of the height information obtained when the target object is in the current posture is compared with a preset value; when the value of the height information obtained when the target object is in the current posture is less than or equal to the preset value, it is determined that the target object is currently in a risk state of falling.

2. The intelligent monitoring method according to claim 1, characterized in that: The obtaining of ranging information corresponding to the ranging part of the target object includes: determining whether the posture of the target object has changed according to the posture information; When the posture of the target object changes, starting a distance measurement module to measure the distance of the distance measurement part of the target object to obtain the distance measurement information; The height variation trend from the distance measuring position to the reference surface is the same as the height variation trend from the center of gravity of the target object to the reference surface.

3. The intelligent monitoring method according to claim 1, characterized in that: The determining whether the target object is currently in a set risk state according to the posture information and the height information further includes: When the value of the height information obtained when the target object is in the current posture is greater than the preset value, determining that the target object is currently in a stationary state; monitoring a duration during which the target object remains in the stationary state; comparing the duration to a time threshold; When the duration exceeds the time threshold, it is determined that the target object is in a risk state of stationary timeout.

4. The intelligent monitoring method according to claim 1, characterized in that: Calculating the height from the distance measurement portion of the target object to a reference surface according to the distance measurement information to obtain height information includes: The height information from the distance measuring part to the reference surface is obtained by calculation according to the distance measuring information, the installation height information of the distance measuring module and the rotation angle information corresponding to the distance measuring module.

5. The intelligent monitoring method according to claim 4, characterized in that: Before calculating the height information of the distance measurement part of the target object to the reference surface according to the distance measurement information, the method further includes: Performing target positioning and target tracking on the target object in the image data to obtain corresponding target positioning data and target tracking data; The ranging position of the target object is determined according to the target positioning data and the target tracking data.

6. The intelligent monitoring method according to claim 5, characterized in that: After performing target positioning and target tracking on the target object in the image data to obtain corresponding target positioning data and target tracking data, and before determining whether the target object is currently in a set risk state based on the posture information and the height information, the method further includes: According to the target positioning data and the target tracking data, the shooting angle of the image acquisition module of the image data is controlled to adjust the position of the target object in the image data.

7. The intelligent monitoring method according to claim 1, characterized in that: Also includes: Obtain at least one of the following temperature data: the temperature of the target object, the temperature of the environment where the target object is located, and the highest temperature of the target object in the scene where the target object is located; The acquired value of the temperature data is compared with a corresponding temperature threshold, and when the temperature data exceeds the corresponding temperature threshold, it is determined that the target object is currently in a risk state of abnormal temperature.

8. An intelligent monitoring device, characterized in that: include: An image acquisition module, used for acquiring image data of a target object; A distance measuring module, configured to measure the distance of the distance measuring part of the target object to obtain the distance measuring information of the target object; a storage module for storing computer programs; A processing module, wherein the processing module obtains the image data and the ranging information, and implements the steps of the intelligent monitoring method according to any one of claims 1 to 7 when running the computer program.

9. The intelligent monitoring device according to claim 8, characterized in that: Also includes a first motor and a second motor; The first motor is used to adjust the orientation of the image acquisition module in a first direction; The second motor is used to adjust the position of the image acquisition module in a second direction, wherein the first direction is perpendicular to the second direction; The first motor and the second motor adjust the position of the target object in the image data according to the control instruction of the processing module.

10. An intelligent monitoring system, characterized in that: It includes the intelligent monitoring device, cloud and terminal device as described in any one of claims 8 to 9, the intelligent monitoring device is used to report the information that the target object is currently in a set risk state to the cloud, and the cloud sends matching early warning information to the corresponding terminal device based on the current risk state of the target object.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by hardware, it can implement the intelligent monitoring method according to any one of claims 1 to 7.

Images